检索结果-内蒙古大学图书馆

Stable and Diverse: A Unified Approach for computerized Adaptive Testing 7

学校读者我要写书评

暂无评论

Stable and Diverse: A Unified Approach for Computerized Adap...

7th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2021

作者： Ning, Yuting Liu, Ye Huang, Zhenya Bi, Haoyang Liu, Qi Chen, Enhong Zhang, Dan University of Science and Technology of China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology China University of Science and Technology of China School of Data Science China IFLYTEK Research IFLYTEK CO. LTD

ISBN: (纸本)9781665441490

computerized Adaptive Testing (CAT), aiming to provide personalized tests for each examinee, is an emerging task in the intelligent education field. A CAT system selects questions step by step according to the knowledge states of each examinee, which are estimated by Cognitive Diagnosis Models (CDM). Most existing methods depend on the performance of a single CDM, which is often unstable. Besides, they may select similar questions to generate a test, which to some extent ignores the diversity of selected questions. To this end, in this paper, we propose a novel framework, namely Ensembled computerized Adaptive Testing (EnCAT). Specifically, EnCAT comprises two components, ensemble part and explore part. In the ensemble part, we ensemble multiple CDMs to determine whether a question is informative, which ensures the stability of CAT process. Then, in the explore part, we learn the question representation from the question content and design a mechanism to quantify the similarity of different questions, which avoids the selection of similar questions and is free of expensive human labeling. Finally, extensive experiments are conducted on a real-world dataset, where the experimental results demonstrate the effectiveness of our proposed EnCAT framework with good performance. © 2021 IEEE.

关键词： computerized Adaptive Testing Diverse Ensemble Learning Stable

Goods Anomaly Detection Based on Multi-Branch Feature Extraction and Foreground Mining

学校读者我要写书评

暂无评论

Goods Anomaly Detection Based on Multi-Branch Feature Extrac...

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Zhiqian Jia Wei Li Zuoyong Li Zhipeng Mu Lihui Lin Shenghua Teng College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Xiamen Air Traffic Management Station of CAAC Xiamen China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science MinjiangUniversity Fuzhou China Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Wuyi University Fujian China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

In recent years, significant advancements have been made in the field of anomaly detection. Expanding anomaly detection tasks to new scenarios has become a development avenue. Anomaly detection for the outer packaging of supermarket goods is a challenging task due to the diversity of goods’ appearances, which results in some detection methods suffering from limited sensitivity to anomalies and inadequate target mining. To address these issues, we propose a novel unsupervised anomaly detection method based on multi-branch feature extraction and foreground cosine structure mining strategy. Firstly, we use anomaly synthesis technique to enhance the model’s perception of anomalies and construct more precise decision boundaries in the feature space. Secondly, a multi-branch feature extractor extracts and integrates multi-level and multi-scale features, providing rich texture and semantic information to improve the model’s adaptability in real-world scenarios. Finally, the foreground cosine loss focuses on target mining while supplementing local structural information, further enhancing the model’s ability to detect subtle anomalies. To validate the effectiveness of the proposed method, extensive experiments were conducted on the GoodsAD dataset, sampled from supermarket scenarios. Experimental results show that this method achieves significant performance in image-level detection and pixel-level localization.

关键词： Location awareness Adaptation models Sensitivity Semantics Education Packaging Feature extraction Information technology Anomaly detection Biomedical imaging

Quiz-based Knowledge Tracing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Shuanghong Chen, Enhong Xu, Bihan Liu, Qi Huang, Zhenya Zhu, Linbo Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science School of Computer Science and Techonology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Anhui Hefei230026 China Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science School of Computer Science and Techonology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230026 China School of Computer Science and Technology Hefei Normal University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230026 China

Knowledge tracing (KT) aims to assess individuals’ evolving knowledge states according to their learning interactions with different exercises in online learning systems (OIS), which is critical in supporting decision-making for subsequent intelligent services, such as personalized learning source recommendation. Existing researchers have broadly studied KT and developed many effective methods. However, most of them assume that students’ historical interactions are uniformly distributed in a continuous sequence, ignoring the fact that actual interaction sequences are organized based on a series of quizzes with clear boundaries, where interactions within a quiz are consecutively completed, but interactions across different quizzes are discrete and may be spaced over days. In this paper, we present the Quiz-based Knowledge Tracing (QKT) model to monitor students’ knowledge states according to their quiz-based learning interactions. Specifically, as students’ interactions within a quiz are continuous and have the same or similar knowledge concepts, we design the adjacent gate followed by a global average pooling layer to capture the intra-quiz short-term knowledge influence. Then, as various quizzes tend to focus on different knowledge concepts, we respectively measure the inter-quiz knowledge substitution by the gated recurrent unit and the inter-quiz knowledge complementarity by the self-attentive encoder with a novel recency-aware attention mechanism. Finally, we integrate the inter-quiz long-term knowledge substitution and complementarity across different quizzes to output students’ evolving knowledge states. Extensive experimental results on three public real-world datasets demonstrate that QKT achieves state-of-the-art performance compared to existing methods. Further analyses confirm that QKT is promising in designing more effective quizzes. Copyright © 2023, The Authors. All rights reserved.

关键词： Students

RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Han Chen, Hua Liu, Wei Yang, Songjie Wang, Gang Yuen, Chau The Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China The Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo315211 China The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China China The School of Electrical and Electronics Engineering Nanyang Technological University Singapore

Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication. Their cost-effectiveness and energy efficiency enable the integration of numerous passive and reflective elements, enabling near-field propagation. In this paper, we tackle the challenges of RIS-aided 3D localization and synchronization in multipath environments, focusing on the near-field of mmWave systems. Specifically, our approach involves formulating a maximum likelihood (ML) estimation problem for the channel parameters. To initiate this process, we leverage a combination of canonical polyadic decomposition (CPD) and orthogonal matching pursuit (OMP) to obtain coarse estimates of the time of arrival (ToA) and angle of departure (AoD) under the far-field approximation. Subsequently, distances are estimated using l1-regularization based on a near-field model. Additionally, we introduce a refinement phase employing the spatial alternating generalized expectation maximization (SAGE) algorithm. Finally, a weighted least squares approach is applied to convert channel parameters into position and clock offset estimates. To extend the estimation algorithm to ultra-large (UL) RIS-assisted localization scenarios, it is further enhanced to reduce errors associated with far-field approximations, especially in the presence of significant near-field effects, achieved by narrowing the RIS aperture. Moreover, the Cramér-Rao Bound (CRB) is derived and the RIS phase shifts are optimized to improve the positioning accuracy. Numerical results affirm the efficacy of the proposed estimation algorithm. © 2024, CC BY.

关键词： Cost effectiveness

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Hao Lu, Junhao Huang, Guoheng Li, Ming Chen, Xuhang Zhong, Guo Tan, Zhengguang Li, Zinuo School of Computer Science and Technology Guangdong University of Technology Guangdong China School of Computer Science and Engineering Huizhou University Huizhou China Zhejiang Institute of Optoelectronics Jinhua China Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China School of Physics Maths and Computing University of Western Australia WA Australia

In Few-Shot Learning (FSL), traditional metric-based approaches often rely on global metrics to compute similarity. However, in natural scenes, the spatial arrangement of key instances is often inconsistent across images. This spatial misalignment can result in mismatched semantic pixels, leading to inaccurate similarity measurements. To address this issue, we propose a novel method called the Layer-Wise Features Metric of Semantic-Pixel Matching (LWFM-SPM) to make finer comparisons. Our method enhances model performance through two key modules: (1) the Layer-Wise Embedding (LWE) Module, which refines the cross-correlation of image pairs to generate well-focused feature maps for each layer;(2)the Semantic-Pixel Matching (SPM) Module, which aligns critical pixels based on semantic embeddings using an assignment algorithm. We conducted extensive experiments to evaluate our method on four widely used few-shot classification benchmarks: miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS. The results indicate that LWFM-SPM achieves competitive performance across these benchmarks. Our code will be publicly available on https://***/Halo2Tang/Code-for-LWFM-SPM. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

Edge Detection of SAR Images Based on Shearlet 7th

学校读者我要写书评

暂无评论

Edge Detection of SAR Images Based on Shearlet

7th China High-resolution Earth Observation Conference, CHREOC 2020

作者： Sun, Zengguo Zhao, Guodong Chen, Weirong Damaševičius, Robertas Woźniak, Marcin Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an China School of Computer Science Shaanxi Normal University Xi’an China China Centre for Resources Satellite Data and Application Beijing China Department of Applied Informatics Vytautas Magnus University Kaunas Lithuania Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44-100 Poland

ISBN: (纸本)9789811657344

Synthetic aperture radar (SAR) has the characteristics of all-weather imaging and is widely used in various fields. However, owe to coherent imaging mechanism, speckle appears in SAR images, which seriously affects the interpretation of images. Due to merits of the strong directional sensitivity and the optimal sparsity, shearlet is used to construct an edge detector for SAR images. The detector firstly converts the constructed even symmetric shearlet into odd symmetry by Hilbert transform, then determines the main direction of the edge according to the odd symmetric shearlet coefficient of the SAR image, and calculates the possibility of edge existence according to both odd and even symmetric shearlet coefficient. Experiments show that, in comparison with the traditional difference-based edge detectors, the proposed edge detector has stronger ability of anti-speckle interference, and can better detect the edge information in SAR images. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speckle

Human behavior recognition based on convolutional long and short time memory network

学校读者我要写书评

暂无评论

Human behavior recognition based on convolutional long and s...

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Zhang, Chuanlin Cao, Kai Huang, Mengge Deng, Tao School of Mathematics and Computer Science Northwest Minzu University Lanzhou China Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University Lanzhou China Key Laboratory of Streaming Data Computing Technologies and Application School of Mathematics and Computer Science Northwest Minzu University Lanzhou China

ISBN: (纸本)9780738110837

Convolutional long and short time memory network is a kind of fusion model, which inherits the excellent spatial feature extraction ability of convolutional neural network, and can effectively complete the processing and classification of time series data by using the memory ability of long and short time memory network to historical data and the unique gating mechanism. This paper uses the human behavior data set collected by the Wireless Data Mining laboratory (WISDM) of Fordham University to predict and classify the six daily human behaviors: walking, jogging, going upstairs, going downstairs, sitting and standing. By comparing with long and short time memory network, convolutional neural network and other deep learning models, the experimental results show that the convolutional long and short time memory network has the best performance among them, which the accuracy reaches 97.43% and has a great improvement in real-time and accuracy. © 2021 IEEE.

关键词： Convolutional neural networks

Beamforming for Movable and Rotatable Antenna Enabled Multi-User Communications

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Ruojing Xu, Yifei Yang, Songjie Chen, Hua Assi, Chadi School of Telecommunications Engineering Xidian University China National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu611731 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo315211 China Concordia University MontrealQCH3G 1M8 Canada

In the development of wireless communication technology, multiple-input multiple-output (MIMO) technology has emerged as a key enabler, significantly enhancing the capacity of communication systems. However, traditional MIMO systems, which rely on fixed-position antennas (FPAs) with spacing limitations, cannot fully exploit the channel variations in the continuous spatial domain, thus limiting the system’s spatial multiplexing performance and diversity. To address these limitations, movable antennas (MAs) have been introduced, offering a breakthrough in signal processing and spatial multiplexing by overcoming the constraints of FPA-based systems. Furthermore, this paper extends the functionality of MAs by introducing movable rotatable antennas (MRAs), which enhance the system’s ability to optimize performance in the spatial domain by adding rotational degrees of freedom. By incorporating a dynamic precoding framework based on both antenna position and rotation angle optimization, and employing the zero-forcing (ZF) precoding method, this paper proposes an efficient optimization approach aimed at improving signal quality, mitigating interference, and solving the non-linear, constrained optimization problem using the sequential quadratic programming (SQP) algorithm. This approach effectively enhances the communication system’s performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Constrained optimization